(opennlp) 02/06: OPENNLP-1850 Address Copilot review on the UAX #29 tokenizer

[kr...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

krickert pushed a commit to branch OPENNLP-1850-2-tokenizer
in repository https://gitbox.apache.org/repos/asf/opennlp.git

commit f48f50f1f69a3dd7a96ec1f3dc71b707a9508400
Author: Kristian Rickert <kr...@gmail.com>
AuthorDate: Sat Jun 20 13:05:02 2026 -0400

    OPENNLP-1850 Address Copilot review on the UAX #29 tokenizer
    
    - WordBoundaryConformanceTest: guard the conformance resource stream with
      Objects.requireNonNull and a clear message instead of an opaque NPE in
      InputStreamReader, and remove the unused NO_BOUNDARY constant.
    - NormalizationProfiles.forLanguage: fail loud on a null language argument at the
      public entry point, with a null-rejection test.
---
 .../java/opennlp/tools/util/normalizer/NormalizationProfiles.java   | 2 ++
 .../opennlp/tools/tokenize/uax29/WordBoundaryConformanceTest.java   | 6 ++++--
 .../opennlp/tools/util/normalizer/NormalizationProfilesTest.java    | 6 ++++++
 3 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/normalizer/NormalizationProfiles.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/normalizer/NormalizationProfiles.java
index 4cd93f287..f46c57dc5 100644
--- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/normalizer/NormalizationProfiles.java
+++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/normalizer/NormalizationProfiles.java
@@ -20,6 +20,7 @@ import java.util.HashMap;
 import java.util.Locale;
 import java.util.Map;
 import java.util.MissingResourceException;
+import java.util.Objects;
 import java.util.Optional;
 import java.util.Set;
 
@@ -83,6 +84,7 @@ public final class NormalizationProfiles {
    * @return The profile, or empty if the language has no Snowball stemmer.
    */
   public static Optional<NormalizationProfile> forLanguage(String language) {
+    Objects.requireNonNull(language, "language");
     String code = language.strip().toLowerCase(Locale.ROOT);
     if (code.length() == 2) {
       try {
diff --git a/opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/tokenize/uax29/WordBoundaryConformanceTest.java b/opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/tokenize/uax29/WordBoundaryConformanceTest.java
index e1bc8231d..80339a801 100644
--- a/opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/tokenize/uax29/WordBoundaryConformanceTest.java
+++ b/opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/tokenize/uax29/WordBoundaryConformanceTest.java
@@ -24,6 +24,7 @@ import java.nio.charset.StandardCharsets;
 import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.List;
+import java.util.Objects;
 
 import org.junit.jupiter.api.Test;
 
@@ -37,7 +38,6 @@ import static org.junit.jupiter.api.Assertions.assertTrue;
 public class WordBoundaryConformanceTest {
 
   private static final int BOUNDARY = 0x00F7; // division sign
-  private static final int NO_BOUNDARY = 0x00D7; // multiplication sign
 
   @Test
   void testOfficialUnicodeWordBreakConformance() throws IOException {
@@ -45,7 +45,9 @@ public class WordBoundaryConformanceTest {
     int passed = 0;
     final List<String> failures = new ArrayList<>();
 
-    try (InputStream in = WordBoundaryConformanceTest.class.getResourceAsStream("WordBreakTest.txt");
+    try (InputStream in = Objects.requireNonNull(
+             WordBoundaryConformanceTest.class.getResourceAsStream("WordBreakTest.txt"),
+             "Missing test resource: WordBreakTest.txt");
          BufferedReader reader =
              new BufferedReader(new InputStreamReader(in, StandardCharsets.UTF_8))) {
       String raw;
diff --git a/opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/normalizer/NormalizationProfilesTest.java b/opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/normalizer/NormalizationProfilesTest.java
index 2d2c02b38..6dbe95260 100644
--- a/opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/normalizer/NormalizationProfilesTest.java
+++ b/opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/normalizer/NormalizationProfilesTest.java
@@ -27,6 +27,7 @@ import opennlp.tools.stemmer.snowball.SnowballStemmer;
 import static org.junit.jupiter.api.Assertions.assertEquals;
 import static org.junit.jupiter.api.Assertions.assertNull;
 import static org.junit.jupiter.api.Assertions.assertSame;
+import static org.junit.jupiter.api.Assertions.assertThrows;
 import static org.junit.jupiter.api.Assertions.assertTrue;
 
 public class NormalizationProfilesTest {
@@ -131,4 +132,9 @@ public class NormalizationProfilesTest {
     assertEquals(19, NormalizationProfiles.supportedLanguages().size());
     assertTrue(NormalizationProfiles.supportedLanguages().containsAll(List.of("eng", "deu", "fra")));
   }
+
+  @Test
+  void testForLanguageRejectsNull() {
+    assertThrows(NullPointerException.class, () -> NormalizationProfiles.forLanguage(null));
+  }
 }